# Privacy Aware Offloading of Deep Neural Networks

arXiv: https://arxiv.org/abs/1805.12024 · HTML: https://mlsanity.com/paper/1805.12024/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2018.

## Built on by (most cited first, 4 of 4)

- [Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems](https://mlsanity.com/paper/2307.01292/) (2023)
- [Enabling Inference Privacy with Adaptive Noise Injection](https://mlsanity.com/paper/2104.02261/) (2021)
- [Privacy Aware Person Detection in Surveillance Data](https://mlsanity.com/paper/2110.15171/) (2021)
- [Selective manipulation of disentangled representations for privacy-aware facial image processing](https://mlsanity.com/paper/2208.12632/) (2022)

## Abstract (arXiv)

Deep neural networks require large amounts of resources which makes them hard to use on resource constrained devices such as Internet-of-things devices. Offloading the computations to the cloud can circumvent these constraints but introduces a privacy risk since the operator of the cloud is not necessarily trustworthy. We propose a technique that obfuscates the data before sending it to the remote computation node. The obfuscated data is unintelligible for a human eavesdropper but can still be classified with a high accuracy by a neural network trained on unobfuscated images.